Uncertainty Quantification and Enhancing Panic Disorder Detection using Ensemble and Resampling Techniques
DOI:
https://doi.org/10.53560/PPASA(62-1)871Keywords:
Panic Attack, Machine Learning, Synthetic Samples, Decision Trees, Predictive Analytics, Mental HealthAbstract
Panic disorder is one of the leading mental health problems that entail serials of extreme fear that can highly hinder an individual's activities of daily life. Sometimes, intervention is very important, understanding the problem is highly crucial. Unfortunately, some methods assist with diagnostics do not provide accuracy in identification. Using machine learning approaches can resolve this problem as accuracy can be improved with data-driven models. This paper used ensemble machine learning models, Random Forest, Bagging Classifier, and Balanced Bagging Classifier to identify panic disorder. Medical datasets usually have a class imbalance problem. Therefore, we performed resampling SMOTE, ADASYN, and Tomek Links. We evaluated these models by accuracy, precision, recall, F1 score, ROC AUC, Cohen's Kappa, uncertainty measures, aleatoric uncertainty, epistemic uncertainty, and predictive entropy. In our results, The Bagging Classifier was out performance with the highest accuracy (99.97%), recall (99.66%), F1-score (99.60%), and Cohen’s Kappa (99.58%), minimal uncertainty metrics (aleatoric: 0.00062, entropy: 0.002003), establishing itself as the optimal model for panic disorder diagnosis. This study proves the effectiveness of ensemble learning and resampling methods for early panic disorder diagnosis and future mental health technologies.
References
A.E. Meuret, J.L. Kroll, and T. Ritz. Panic disorder comorbidity with medical conditions and treatment implications. Annual Review of Clinical Psychology 13(1): 209-240 (2017).
L. Spytska. Exploration of personality characteristics of individuals with panic attacks: A personality profile study. Journal of Infant, Child, and Adolescent Psychotherapy 84(1): 84-94 (2025).
M.G. Abrignani, N. Renda, V. Abrignani, A. Raffa, S. Novo, and R. Lo Baido. Panic disorder, anxiety, and cardiovascular diseases. Clinical Neuropsychiatry 11(5): 130-144 (2014).
A. M. Krypotos, G. Mertens, D. Matziarli, I. Klugkist, I. M. Engelhard. Fear generalization in individuals with subclinical symptoms of panic disorder. Behaviour Research and Therapy 1(184): 104649 (2025).
P. Porcelli. Fear, anxiety, and health-related consequences after the COVID-19 epidemic. Clinical Neuropsychiatry 17(2): 103-111(2020).
J.F. Brosschot, B. Verkuil, and J.F. Thayer. The default response to uncertainty and the importance of perceived safety in anxiety and stress: An evolution-theoretical perspective. Journal of Anxiety Disorders 41(1): 22-34 (2016).
M.G. Craske, M.B. Stein, T.C. Eley, M.R. Milad, A. Holmes, R.M. Rapee, and H.U. Wittchen. Anxiety disorders. Nature Reviews. Disease Primers 3: 17024 (2017).
B. Bandelow, D. Baldwin, M. Abelli, C. Altamura, B. Dell’Osso, K. Domschke, N.A. Fineberg, E. Grünblatt, M. Jarema, E. Maron, and D. Nutt. Biological markers for anxiety disorders, OCD, and PTSD–a consensus statement. Part I: Neuroimaging and genetics. The World Journal of Biological Psychiatry 17(5): 321-365 (2016).
S.G. Hofmann (Ed.). An Introduction to Modern CBT: Psychological Solutions to Mental Health Problems. John Wiley & Sons (2011).
N.R. Rayburn and M.W. Otto. Cognitive-behavioral therapy for panic disorder: A review of treatment elements, strategies, and outcomes. CNS Spectrums 8(5): 356-362 (2003).
S. G. Farri, L. Derby, M. M. Kibbey. Getting comfortable with physical discomfort: A scoping review of interoceptive exposure in physical and mental health conditions. Psychological Bulletin. 151(2):131(2025).
G. Chouinard and V.A. Chouinard. A new classification of selective serotonin reuptake inhibitor withdrawal. Psychotherapy and Psychosomatics 84(2): 63-71 (2015).
S.S. Clevenger, D. Malhotra, J. Dang, B. Vanle, and W.W. Ishak. The role of selective serotonin reuptake inhibitors in preventing relapse of major depressive disorder. Therapeutic Advances in Psychopharmacology 8(1): 49-58 (2018).
D. Lochmann and T. Richardson. Selective serotonin reuptake inhibitors. In: Antidepressants. Handbook of Experimental Pharmacology. M. Macaluso and S. Preskorn (Eds.). Volum 250. Springer Nature Switzerland pp. 135-144 (2018).
U. Madububambachu, A. Ukpebor, and U. Ihezue. Machine learning techniques to predict mental health diagnoses: A systematic literature review. Clinical Practice and Epidemiology in Mental Health 20: e17450179315688 (2024).
F. Akhtar, M.B.B. Heyat, A. Sultana, S. Parveen, H. Muhammad Zeeshan, S.F. Merlin, B. Shen, D. Pomary, J. Ping Li, and M. Sawan. Medical intelligence for anxiety research: Insights from genetics, hormones, implant science, and smart devices with future strategies. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 14(6): e1552 (2024).
G. Prieto-Avalos, N.A. Cruz-Ramos, G. Alor-Hernandez, J.L. Sánchez-Cervantes, L. Rodriguez-Mazahua, and L.R. Guarneros-Nolasco. Wearable devices for physical monitoring of heart: A review. Biosensors 12(5): 292 (2022).
E.A. Poweleit, A.A. Vinks, and T. Mizuno. Artificial intelligence and machine learning approaches to facilitate therapeutic drug management and model-informed precision dosing. Therapeutic Drug Monitoring 45(2): 143-150 (2023).
N.K. Iyortsuun, S.H. Kim, M. Jhon, H.J. Yang, and S. Pant. A review of machine learning and deep learning approaches on mental health diagnosis. Healthcare 11(3): 285 (2023).
K. Nova. Machine learning approaches for automated mental disorder classification based on social media textual data. Contemporary Issues in Behavioral and Social Sciences 7(1): 70-83 (2023).
D. Nurmalasari, H.R. Yuliantoro, and D.H. Qudsi. Improving panic disorder classification using SMOTE and random forest. Journal of Applied Informatics and Computing 8(2): 272-279 (2024).
P. Sahebi. Enhancing user experience for real-time panic attack detection with wearable technology: A human-computer interaction approach with machine learning integration. International Journal of Advanced Human-Computer Interaction 2(2): 55-66 (2024).
E.H. Jang, K.W. Choi, A.Y. Kim, H.Y. Yu, H.J. Jeon, and S. Byun. Automated detection of panic disorder based on multimodal physiological signals using machine learning. ETRI Journal 45(1): 105-118 (2023).
I. Lazarou, A.L. Kesidis, G. Hloupis, and A. Tsatsaris. Panic detection using machine learning and real-time biometric and spatiotemporal data. ISPRS International Journal of Geo-Information 11(11): 552 (2022).
C.H. Tsai, P.C. Chen, D.S. Liu, Y.Y. Kuo, T.T. Hsieh, D.L. Chiang, F. Lai, and C.T. Wu. Panic attack prediction using wearable devices and machine learning. Development and cohort study. JMIR Medical Informatics 10(2): e33063 (2022).
E.W. McGinnis, B. Loftness, S. Lunna, I. Berman, S. Bagdon, G. Lewis, M. Arnold, C.M. Danforth, P.S. Dodds, M. Price, and W.E. Copeland. Expecting the unexpected: Predicting panic attacks from mood, Twitter, and Apple Watch data. IEEE Open Journal of Engineering in Medicine and Biology 5(1): 14-20 (2024).
I.H. Bell, S.L. Rossell, J. Farhall, M. Hayward, M.H. Lim, S.F. Fielding-Smith and N. Thomas. Pilot randomised controlled trial of a brief coping-focused intervention for hearing voices blended with smartphone-based ecological momentary assessment and intervention (SAVVy): Feasibility, acceptability and preliminary clinical outcomes. Schizophrenia Research 216: 479-487 (2020).
D.J. Robinaugh, M.J. Ward, E.R. Toner, M.L. Brown, O.M. Losiewicz, E. Bui, and S.P. Orr. Assessing vulnerability to panic: A systematic review of psychological and physiological responses to biological challenges as prospective predictors of panic attacks and panic disorder. General Psychiatry 32(6): e100140 (2019).
S. Jang, T.H. Sun, S. Shin, H.J. Lee, Y.B. Shin, J.W. Yeom, Y.R. Park, and C.H. Cho. A digital phenotyping dataset for impending panic symptoms: A prospective longitudinal study. Scientific Data 11(1): 1264 (2024).
K.S. Na, S.E. Cho, and S.J. Cho. Machine learning-based discrimination of panic disorder from other anxiety disorders. Journal of Affective Disorders 278: 1-4 (2021).
S. Ogawa. Predicting dropout from cognitive behavioral therapy for panic disorder using machine learning algorithms. Journal of Clinical Medicine Research 16(5): 251 (2024).
C.H. Tsai, P.C. Chen, D.S. Liu, Y.Y Kuo, T.T Hsieh, D.L Chiang, F. Lai and C.T Wu. Panic attack prediction using wearable devices and machine learning: development and cohort study. JMIR Medical Informatics 10(2): e33063 (2022).
C. Pae, H.J. Kim, M. Bang, C.I. Park, and S.H. Lee. Predicting treatment outcomes in patients with panic disorder: Cross-sectional and two-year longitudinal structural connectome analysis using machine learning methods. Journal of Anxiety Disorders 106(2): 102895 (2024).
D.J. Robinaugh, J. Haslbeck, L.J. Waldorp, J.J. Kossakowski, E.I. Fried, A.J. Millner, R.J. McNally, O. Ryan, J. de Ron, H.L. van der Maas and E.H. van Nes. Advancing the network theory of mental disorders: A computational model of panic disorder. Psychological Review 131(6): 1482 (2024).
R. Rajendran and A. Karthi. Heart disease prediction using entropy-based feature engineering and ensembling of machine learning classifiers. Expert Systems with Applications 20(7): 117882 (2022).
X. Peng, W. Wu, Y. Zheng, J. Sun, T. Hu, and P. Wang. Correlation analysis of land surface temperature and topographic elements in Hangzhou, China. Scientific Reports 10(1): 10451 (2020).
O.L. Usman, R.C. Muniyandi, K. Omar, and M. Mohamad. Gaussian smoothing and modified histogram normalization methods to improve neural-biomarker interpretations for dyslexia classification mechanism. PLoS One 16(2): e0245579 (2021).
F. Gurcan and A. Soylu. Synthetic boosted resampling using deep generative adversarial networks: A novel approach to improve cancer prediction from imbalanced datasets. Cancers 16(23): 4046 (2024).
S. Nouas, L. Oukid, and F. Boumahdi. Syngo: Synthetic genetic oversampling technique for textual data. Social Network Analysis and Mining 15(1): 9 (2025).
S.S. Dhaliwal, A.A. Nahid, and R. Abbas. Effective intrusion detection system using XGBoost. Information 9(7): 149 (2018).
A.S. More and D.P. Rana. Review of random forest classification techniques to resolve data imbalance. Proceedings of the 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM) pp. 72-78 (2017).
S. Hido, H. Kashima, and Y. Takahashi. Roughly balanced Bagging for imbalanced data. Statistical Analysis and Data Mining. The ASA Data Science Journal 2(5‐6): 412-426 (2009).
E. Hüllermeier and W. Waegeman. Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods. Machine Learning 110(3): 457-506 (2021).
